The retrieval augmented generation (RAG) framework addresses an ambiguity in user queries in QA systems by retrieving passages that cover all plausible interpretations and generating comprehensive responses based on the passages. However, our preliminary studies reveal that a single retrieval process often suffers from low quality results, as the retrieved passages frequently fail to capture all plausible interpretations. Although the iterative RAG approach has been proposed to address this problem, it comes at the cost of significantly reduced efficiency. To address these issues, we propose the diversify-verify-adapt (DIVA) framework. DIVA first diversifies the retrieved passages to encompass diverse interpretations. Subsequently, DIVA verifies the quality of the passages and adapts the most suitable approach tailored to their quality. This approach improves the QA systems accuracy and robustness by handling low quality retrieval issue in ambiguous questions, while enhancing efficiency.

Long video understanding is a significant and ongoing challenge in the intersection of multimedia and artificial intelligence. Employing large language models (LLMs) for comprehending video becomes an emerging and promising method. However, this approach incurs high computational costs due to the extensive array of video tokens, experiences reduced visual clarity as a consequence of token aggregation, and confronts challenges arising from irrelevant visual tokens while answering video-related questions. To alleviate these issues, we present an Interactive Visual Adapter (IVA) within LLMs, designed to enhance interaction with fine-grained visual elements. Specifically, we first transform long videos into temporal video tokens via leveraging a visual encoder alongside a pretrained causal transformer, then feed them into LLMs with the video instructions. Subsequently, we integrated IVA, which contains a lightweight temporal frame selector and a spatial feature interactor, within the internal blocks of LLMs to capture instruction-aware and fine-grained visual signals. Consequently, the proposed video-LLM facilitates a comprehensive understanding of long video content through appropriate long video modeling and precise visual interactions. We conducted extensive experiments on nine video understanding benchmarks and experimental results show that our interactive visual adapter significantly improves the performance of video LLMs on long video QA tasks. Ablation studies further verify the effectiveness of IVA in long and short video understandings.

General Motors is taking Google's AI chatbot on the road. The automaker announced today that it's using Google Cloud's Dialogflow to automate some non-emergency OnStar features like navigation and call routing. Crucially, the automaker claims the bot can pinpoint keywords indicating an emergency situation and "quickly route the call" to trained humans when needed. GM says the system frees up OnStar Advisors to spend more time with customers requiring a live human. According to GM, the OnStar Interactive Virtual Assistant (IVA) has used Google Cloud's Dialogflow under the hood since IVA's 2022 launch.

I recently had a scare during the holidays when my octogenarian father, visiting from out of town, fell in the kitchen during our Christmas Eve gathering. My heart skipped a beat at that moment and 10 things ran through my mind about what to do next, like wishing we had a doctor in the family! So going to the ER was not the answer. However, we had concerns for him, and I needed some peace of mind. Could I give him Tylenol, or would that interfere with his current medicines?

Airmeez announced they will be working with SoundHound AI, Inc. technology to bring a seamless conversational AI experience to software-as-a-service intelligent virtual assistant, notification and customer engagement solutions. Intelligent Virtual Assistants (IVAs) are AI-powered assistants that achieve the purpose of interactions while generating personalized responses by combining analytics and cognitive computing based on individual customer information, past conversations, and location. SoundHound's advanced voice AI will now be deployed through Airmeez offerings, which include a customer communications platform as a service for building custom IVA, notification and other communication solutions using a no-code drag-and-drop design tool. This voice-enablement will allow callers to interact with Airmeez applications, providing award-winning accuracy of intent detection, convenience and cost savings in healthcare, government, education and other markets. SoundHound's proprietary Speech-to-Meaning system will allow Airmeez to deliver a faster and more positive caller experience, an improved efficiency of call centers, and reduce staffing challenges and costs for their customers.

Today, organizations understand the pressing need to expand and enhance their digital sales and support solutions to address new customer demands. Consumers are demanding anytime, anywhere services. While many companies have bolstered their web and mobile presence, customers still turn to the contact center when they need additional support. Given this trend, businesses must modernize and improve their contact center capabilities. Five9 recently held a joint analyst call with several of its customer to share how various companies were evolving their contact centers.

Understanding human behavior and monitoring mental health are essential to maintaining the community and society's safety. As there has been an increase in mental health problems during the COVID-19 pandemic due to uncontrolled mental health, early detection of mental issues is crucial. Nowadays, the usage of Intelligent Virtual Personal Assistants (IVA) has increased worldwide. Individuals use their voices to control these devices to fulfill requests and acquire different services. This paper proposes a novel deep learning model based on the gated recurrent neural network and convolution neural network to understand human emotion from speech to improve their IVA services and monitor their mental health.

Mining the latent intentions from large volumes of natural language inputs is a key step to help data analysts design and refine Intelligent Virtual Assistants (IVAs) for customer service and sales support. We created a flexible and scalable clustering pipeline within the Verint Intent Manager (VIM) that integrates the fine-tuning of language models, a high performing k-NN library and community detection techniques to help analysts quickly surface and organize relevant user intentions from conversational texts. The fine-tuning step is necessary because pre-trained language models cannot encode texts to efficiently surface particular clustering structures when the target texts are from an unseen domain or the clustering task is not topic detection. We describe the pipeline and demonstrate its performance and ability to scale on three real-world text mining tasks. As deployed in the VIM application, this clustering pipeline produces high quality results, improving the performance of data analysts and reducing the time it takes to surface intentions from customer service data, thereby reducing the time it takes to build and deploy IVAs in new domains.

Women in AI Ireland in collaboration with Women in Research Ireland present this live virtual event: Artificial Intelligence #BreaktheBias. With this event, we celebrate technical competencies in Artificial Intelligence for both industry and academia by highlighting different pathways from academia to industry and challenges therein to mark the International Women's Day 2022! Dr. Georgiana Ifrim is an Associate Professor at the School of Computer Science, UCD, co-lead of the SFI Centre for Research Training in Machine Learning (ML-Labs) and SFI Funded Investigator with the Insight Centre for Data Analytics and VistaMilk SFI Centre. Dr Ifrim holds a PhD and MSc in Machine Learning, from Max-Planck Institute for Informatics, Germany, and a BSc in Computer Science, from University of Bucharest, Romania. Her research focuses on effective approaches for large scale sequence learning, time series classification and text mining.

Make way for interactive virtual assistants (IVAs). But can chatbots change the customer experience? Can IVAs like Amelia go beyond the limitations of chatbots? There is plenty to consider. In 50 years, chatbots have evolved first to engage users in dialogues for customer service in many fields and now to conversations on personal medication information.